Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2408 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0827. Min Act: -0.1700

Data Index: 860606 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0243. Min Act: -0.1700

Data Index: 7390580 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0326. Min Act: -0.1696

Data Index: 8056606 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0043. Min Act: -0.1700

Data Index: 7329691 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.0827. Min Range: -1.0827

Max Act: 1.0240. Min Act: -0.1700

Data Index: 4139681 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9928. Min Act: -0.1700

Data Index: 1445682 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9952. Min Act: -0.1700

Data Index: 530118 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9945. Min Act: -0.1700

Data Index: 3199296 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9624. Min Act: -0.1700

Data Index: 4562053 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9467. Min Act: -0.1700

Data Index: 6036831 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9634. Min Act: -0.1700

Data Index: 4506987 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9701. Min Act: -0.1700

Data Index: 8323260 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9517. Min Act: -0.1700

Data Index: 7905186 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9695. Min Act: -0.1700

Data Index: 4684268 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9614. Min Act: -0.1700

Data Index: 6783826 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9461. Min Act: -0.1697

Data Index: 1433507 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9401. Min Act: -0.1691

Data Index: 2013575 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9492. Min Act: -0.1700

Data Index: 575602 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9492. Min Act: -0.1700

Data Index: 577301 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.0827. Min Range: -1.0827

Max Act: 0.9535. Min Act: -0.1693

Data Index: 6253570 (Open Web Text)

Max Activating Token Index: 3